Abstract Objective: Trichomoniasis can increase the risk of getting or spreading other sexually transmitted infections. It can cause genital inflammation that can increase the likelihood of infection with HIV or passing HIV on to a sex partner. The present study used QSAR modeling to study benzimidazole derivatives as potent inhibitors of trichomonicidal activity. A set of 10 compounds was randomly removed from the dataset to be used as the prediction set (PSET). The remaining 60 compounds were utilized as the training set (TSET). Methods: Genetic algorithms, artificial neural networks (ANN), multiple linear regression (MLR), partial least squares (PLS), principal component regression (PCR) and a least absolute shrinkage and selection operator (LASSO) were used to create the QSAR models. Geometry optimization of compounds was carried out using the B3LYP method employing a 6-31G (2d) basis set. HyperChem, Gaussian 03W and Dragon (version 5.5) software were used for geometric optimization of the molecules and calculation of the quantum chemical descriptors. Unscrambler was used for analysis of data. Results: The MLR method obtained a root mean square error (RMSE) for calibration of 0.0803 and R2 of 0.99. The R2 and RMSE of calibration using PCR were 0.58 and 0.5236, respectively. Conclusion: The results found that the ANN and MLR models were the most favorable of the methods tested and are suitable for use in QSAR models.